© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 16011
    Prev
    Next
    INDEX
    Explanations

    impossible / unlikely

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron fires on words that denote removal or exclusion—e.g. stepping down, being eliminated, or otherwise taken out of office, a list, or a position.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وا
    0.72
     judicious
    0.69
     sometimes
    0.67
     را
    0.67
     THEN
    0.64
     quelquefois
    0.64
     nhấn
    0.64
    ⁄
    0.63
     dign
    0.63
     иногда
    0.62
    POSITIVE LOGITS
     невозможно
    1.43
    因為
    1.38
    因为
    1.36
    Impossible
    1.36
    由於
    1.33
    impossible
    1.32
     क्योंकि
    1.31
    由于
    1.29
    due
    1.28
    because
    1.28
    Activations Density 0.779%

    No Known Activations